Patent Application
20220365508
The disclosure herein relates generally to log processing, and more particularly to service console log processing devices, systems, and methods capable of improving the efficiency of diagnosis and repair of malfunctioning equipment.
Existing production mail equipment and other industrial equipment in various fields, as well as new equipment sold to process production mail, primarily use a decades-old service paradigm where operators run scheduled jobs and typically only request service for the equipment when the equipment stops, either intermittently or entirely, or otherwise is in need of repair due to one or more malfunctions.
Until the malfunction is resolved, such equipment either continues to be operated sub-optimally (e.g., in a degraded performance state) or is left idle (e.g., unused entirely). Due to the fact that it is oftentimes not possible to resolve equipment malfunctions instantaneously, whether due to scheduling restrictions, parts, availability, etc., the delay associated with performing repairs on malfunctioning equipment causes a reduction in output or performance of equipment, under-utilization of such equipment, and/or reduces the return on investment (ROI) below an anticipated, or expected level. Given a lack of information regarding the cause of the malfunction for known equipment, service technicians often spend considerable amounts of time merely trying to troubleshoot the malfunction. Additionally, many other types of industrial equipment produce logging messages and other types of messages without a consistent formatting of the logs. This causes many issues with analyzing the different logging messages that are reported because scripts, software, and other automation tools must be customized for each individual type of equipment versus a uniform analysis tool.
As such, there exists a need for devices, systems, and methods capable of improving the efficiency of diagnosis and repair of malfunctioning equipment.
According to a first example embodiment, a system for reducing downtime is provided, the system comprising: one or more displays; a plurality of industrial machines configured to generate logging messages, each logging message comprising information regarding a corresponding one of the plurality of industrial machines; one or more sensors positioned on or proximate to one or more of the plurality of industrial machines, wherein each sensor is configured to detect one or more operational parameters for the one or more of the plurality of industrial machines to which the sensor is positioned on or proximate to; one or more edge agents; and one or more central controllers. Each edge agent is associated with one or more industrial machines of the plurality of industrial machines and comprises: one or more processors in communication with the one or more industrial machines with which the edge agent that comprises the one or more processors is associated; and one or more transceivers configured to receive sensor information regarding one or more operational parameters from at least some of the one or more sensors and/or the logging messages from the one or more industrial machines with which the edge agent that comprises the one or more transceivers is associated. Each of the one or more central controllers comprises: one or more processors in communication with at least some of the one or more edge agents; and one or more transceivers. Each of the central controllers is configured to: receive, via the one or more transceivers of the one or more central controllers, the logging messages and the sensor information from the one or more edge agents in communication therewith; transform, via the one or more processors of the one or more central controllers, the logging messages and the sensor information into standardized logging messages, each of which has a same formatting; analyze the standardized logging messages to determine a current or anticipated error condition associated with one or more of the plurality of industrial machines; and automatically transmit, via the one or more transceivers of the one or more central controllers, an alert and/or a notification regarding the current or anticipated error condition to the one or more displays. The one or more displays are configured to receive and display the alert and/or the notification to one or more users of the system.
In some embodiments of the system, the one or more displays comprise a display of a mobile personal electronic device.
In some embodiments of the system, the mobile personal electronic device is configured to transmit one or more commands from the one or more users to deactivate, or change an operational state of, any of the plurality of industrial machines.
In some embodiments of the system, the one or more central controllers comprise a database that includes instances of historical error conditions and historical logging messages that were generated before, during, and/or after each instance of the historical error conditions for any of the plurality of industrial machines.
In some embodiments of the system, the one or more processors of the one or more central controllers are configured to determine the current or anticipated error condition by comparing the standardized logging messages to the historical logging messages.
In some embodiments of the system, the one or more processors of the one or more central controllers are configured to compare the standardized logging messages to the historical logging messages to identify series, or sequences, of the standardized logging messages that are substantially similar to the historical logging messages that were generated before, during, and/or after each instance of the historical error conditions.
In some embodiments of the system, the one or more processors of the one or more central controllers are configured to compare the standardized logging messages to the historical logging messages to identify series, or sequences, of the standardized logging messages that are identical to the historical logging messages that were generated before, during, and/or after each instance of the historical error conditions.
In some embodiments of the system, the plurality of industrial machines comprise at least two different types of industrial machines.
In some embodiments of the system, each edge agent is configured to receive logging messages from each of the different types of industrial machines.
In some embodiments of the system, each edge agent is located in a same location as the one or more industrial machines from which the edge agent is configured to receive the logging messages.
In some embodiments of the system, the plurality of industrial machines comprises one or more industrial mail processing machines.
In some embodiments of the system, the one or more transceivers of the one or more central controllers are configured to transmit one or more commands to any of the plurality of industrial machines for which the current or anticipated error condition is determined, wherein any of the plurality of industrial machines that receives the one or more commands are configured to automatically perform one or more actions to correct, or prevent an occurrence of, the current or anticipated error condition.
In some embodiments of the system, the one or more actions comprise any of powering on, powering off, power cycling, and/or starting or stopping operation of a part or component associated with any of the plurality of industrial machines that receives the one or more commands.
In some embodiments of the system, the one or more processors of the one or more central controllers are configured to generate, and the one or more transceivers of the one or more central controllers are configured to transmit, a work order to a service technician for any of the plurality of industrial machines with which the current or anticipated error condition is associated, the work order comprising instructions for the service technician to correct, or prevent an occurrence of, the current or anticipated error condition.
In some embodiments of the system, the one or more displays are configured to receive information regarding a performance of one or more of the plurality of industrial machines and to display the information regarding the performance of the one or more of the plurality of industrial machines.
In some embodiments of the system, the logging messages generated by the plurality of industrial machines and/or the one or more operational parameters detected by the one or more sensors comprises and/or indicates one or more error conditions associated with one or more of the plurality of industrial machines.
According to a second example embodiment, a method of reducing downtime is provided, the method comprising steps of: performing, using a plurality of industrial machines, one or more industrial activities, wherein each industrial machine can generate logging messages, each logging message comprising information regarding a corresponding one of the plurality of industrial machines that generates the logging message; positioning one or more sensors on or proximate to one or more of the plurality of industrial machines, wherein each sensor detects one or more operational parameters for the one or more of the plurality of industrial machines to which the sensor is positioned on or proximate to; providing one or more edge agents, each of which is associated with one or more industrial machines of the plurality of industrial machines and comprises one or more processors and one or more transceivers; connecting the one or more processors in communication with the one or more industrial machines with which the edge agent that comprises the one or more processors is associated; receiving, via the one or more transceivers, sensor information regarding one or more operational parameters from at least some of the one or more sensors and/or the logging messages from the one or more industrial machines with which the edge agent that comprises the one or more transceivers is associated; connecting one or more central controllers in communication with at least some of the one or more edge agents; receiving, via the one or more transceivers of the one or more central controllers, the logging messages and the sensor information from the one or more edge agents in communication therewith; transforming, using the one or more processors of the one or more central controllers, the logging messages and the sensor information into standardized logging messages, each of which has a same formatting; analyzing, using the one or more processors of the one or more central controllers, the standardized logging messages to determine a current or anticipated error condition associated with one or more of the plurality of industrial machines; transmitting, automatically and via the one or more transceivers of the one or more central controllers, an alert and/or a notification regarding the current or anticipated error condition to one or more displays; and displaying, on the one or more displays, the alert and/or the notification to one or more users.
In some embodiments of the method, the one or more displays comprise a display of a mobile personal electronic device.
In some embodiments of the method, the mobile personal electronic device comprises an input and a transceiver, the method comprising transmitting one or more commands from the one or more users to deactivate, or change an operational state of, any of the plurality of industrial machines.
In some embodiments, the method comprises providing, in communication with the one or more central controllers, a database that includes instances of historical error conditions and historical logging messages that were generated before, during, and/or after each instance of the historical error conditions for any of the plurality of industrial machines.
In some embodiments, the method comprises determining, using the one or more processors of at least one of the one or more central controllers, the current or anticipated error condition by comparing the standardized logging messages to the historical logging messages.
In some embodiments, the method comprises comparing, using the one or more processors of at least one of the one or more central controllers, the standardized logging messages to the historical logging to identify series, or sequences, of the standardized logging messages that are substantially similar to the historical logging messages that were generated before, during, and/or after each instance of the historical error conditions.
In some embodiments, the method comprises comparing, using the one or more processors of at least one of the one or more central controllers, the standardized logging messages to the historical logging messages to identify series, or sequence, of the standardized logging messages that are identical to the historical logging messages that were generated before, during, and/or after each instance of the historical error conditions.
In some embodiments of the method, the plurality of industrial machines comprise at least two different types of industrial machines.
In some embodiments, the method comprises receiving, for each edge agent, logging messages from each of the different types of industrial machines.
In some embodiments of the method, each edge agent is located in a same location as the one or more industrial machines from which the edge agent receives the logging messages.
In some embodiments of the method, the plurality of industrial machines comprises one or more industrial mail processing machines.
In some embodiments, the method comprises: transmitting, using one or more transceivers of at least one of the one or more central controllers, one or more commands to any of the plurality of industrial machines for which the current or anticipated error condition is determined; and automatically performing, at any of the plurality of industrial machines that receives the one or more commands, one or more actions to correct, or prevent an occurrence of, the current or anticipated error condition.
In some embodiments of the method, the one or more actions comprise any or powering on, powering off, power cycling, and/or starting or stopping operation of a part or component associated with any of the plurality of industrial machines that receives the one or more commands.
In some embodiments, the method comprises: generating, using the one or more processors of at least one of the one or more central controllers, a work order for any of the plurality of industrial machines with which the current or anticipated error condition is associated, wherein the work order comprises instructions for a service technician to perform to correct, or prevent an occurrence of, the current or anticipated error condition; and transmitting, using the one or more transceivers of the at least one of the one or more central controllers, the work order to the service technician.
In some embodiments, the method comprises: receiving, at the one or more displays, information regarding a performance of one or more of the plurality of industrial machines; and displaying, on the one or more displays, the information regarding the performance of the one or more of the plurality of industrial machines.
In some embodiments of the method, the logging messages generated by the plurality of industrial machines and/or the one or more operational parameters detected by the one or more sensors comprises and/or indicates one or more error conditions associated with one or more of the plurality of industrial machines.
The subject matter herein provides example service console logging message processing systems and methods. Such systems and methods use so-called “edge agents” that are installed on or in communication with industrial machines or industrial equipment in the field (e.g., on the manufacturing floor, warehouse, or any other suitable location where industrial machines are located and operated to perform an industrial task). Edge agents include hardware and software designed to receive log data (e.g., logging messages, log messages, or logs) from one or more of the industrial machines, either alone or in conjunction with sensor information received from sensors that are positioned on or associated with (e.g., positioned adjacent to, in order to detect operational anomalies) the industrial machines. The edge agents transmit or stream (e.g., in real-time) the logging data to a central controller, which can also be referred to herein as a central processing engine.
The logging data and/or sensor information contain information and data related to the health (e.g., remaining useful life, based on reliability data), operational status (e.g., on/off), performance (e.g., throughput or productivity metrics), etc. of each of the industrial machines with which the sensors are associated, or from which the logging data is received. The central controller receives the logging data from one or more edge agents. The edge agents can be co-located with the central controller or at any place around the world where industrial machines, about which logging data and/or sensor information is desired to be known, are located. Thus, the edge agents are connected to the central controller via communication networks, such as the Internet. Once the logging data and/or sensor information is received at the central controller, the logging data and/or sensor information is transformed into standardized logging messages, all of which have the same format. In some embodiments, one or more edge agent is configured to pre-process certain information (e.g., of the logging data and/or the sensor information) prior to such information being sent to the central controller.
Different types of industrial machines, and even industrial machines that are of a same type but are produced by different manufacturers, are known to produce logging data regarding the health, operational status, performance, etc. of the industrial machine that is different in terms of, for example and without limitation, message formatting, message content, and/or even the parameters being monitored. Such logging data regarding the operation of such industrial machines, is undeniably useful, but it is at present not possible for known systems to process and understand the data contained therein when the logging data may be presented and/or transmitted in any of a plurality of different formats.
Thus, the central controller advantageously receives the logging data and/or sensor information in a so-called “raw” form, meaning that the information contained therein is unformatted, and transforms the logging data and/or the sensor information into standardized logging messages, each of which has the same formatting to provide enhanced ability to categorize, classify, index, and/or search to allow for the available information to be utilized to determine a current or anticipated error condition. The term “current” means happening in real-time, or an ongoing error condition that has not yet been remedied, even if the industrial machine has been taken offline (e.g., intentionally rendered inoperable) due to the error condition. The term “anticipated” means an error condition that has not yet happened, but which is expected to happen within a specified window of time; this is often referred to as predictive failure analysis (PFA) and is exceptionally helpful in maintaining the operational status of industrial machines by anticipating failures before they happen so that any necessary parts can be ordered and service technicians can be assigned to carry out the repair at a time that is pre-planned to minimize downtime for the industrial machine and also of other industrial machines that may be interoperable with the industrial machine that needs the preventive service to be performed.
After being generated, the standardized logging messages are indexed and stored for further processing. Among the advantages provided by the presently disclosed subject matter is that it is now possible to detect error conditions and other negative events (e.g., events that indicate the industrial machine is still operable, but the remaining useful life is or has been degraded) in the industrial machine during or, preferably, before the actual occurrence of the error conditions or negative events, so that staff (e.g., service technicians or other qualified maintenance repair personnel) can be alerted to the current or anticipated error condition and also aid in performing proactive maintenance to remedy the error condition before the industrial machine experiences unscheduled downtime, which can have a significant negative impact on productivity on not only the impacted industrial machine but also to other industrial machinery that may be associated with (e.g., operates as part of an assembly line with) the impacted industrial machine.
In some embodiments, the central controller transmits commands to any of the industrial machines that may be impacted by the current or anticipated error condition, such that the impacted industrial machines automatically perform one or more actions to correct or, preferably, prevent, an occurrence of the current or anticipated error condition. Examples of such commands include, for example and without limitation, power off, power on, power cycle, and/or start or stop (e.g., engage or disengage, activate or deactivate, etc.) operation of individual parts, components, and/or subsystems of impacted industrial equipment based on the processing of the standardized logging messages and whether any error conditions are detected or anticipated. In some such embodiments, the central controller transmits data, such as an alert or notification, to a display for visualization, performance monitoring, etc. of the industrial machines. In some cases, the edge agent(s) implement certain prescribed corrective actions immediately, based on pre-processed information contained in the logging data and/or sensor information, prior to the logging data and/or sensor information being sent to the central controller.
Referring to
Each edge agent 100 is in communication with one or more of (e.g., a plurality of) of the industrial machines 10 and/or with one or more of (e.g., a plurality of) the sensors 200. In some embodiments, there are a plurality of geographically distanced locations at which one or more industrial machines 10 are operating; in such embodiments, there may be a single edge agent 100, or a plurality of edge agents 100, installed at least location.
Each sensor 200 is installed on an industrial machine 10 or positioned at a location sufficiently proximate to one or more industrial machines 10 to detect one or more operational parameters (e.g., a vibration, speed, etc.) of any of the one or more industrial machines 10 to which such sensor is in sufficiently close proximity, these one or more operational parameters indicating an error condition for the one or more industrial machines 10 and/or an out-of-specification or out-of-tolerance operational state of the one or more industrial machines 10 that indicates a failure, malfunction, and/or error condition is likely to occur on the one or more industrial machines 10 within a prescribed period of time. Sensors 200 can be of a type that transmits a periodic, continuous, and/or real-time, raw data value to the edge agent 100 to which the sensor 200 is connected. Sensors 200 can be of a type that comprises a processor, memory, and the like (e.g., as a system-on-chip, or SoC), and is configured to perform a level of diagnostic processing for the one or more operational parameters being detected, such that such sensors 200 send alerts, whether formatted or in a raw, unprocessed, form to the edge agent with which the sensor 200 is in communication only when an out-of-specification or out-of-tolerance operational state of the one or more industrial machines 10 has been detected. Any mixture of such sensors 200 can be provided without limitation.
Each central controller 300 is in communication, via the communication network 50, with each of (e.g., all of), or a subset consisting of less than all of, the edge agents 200, which can be co-located or located at different locations (e.g., different cities, states, countries, etc.) from each other.
In some embodiments, there is only a single edge agent 100, with or without any sensors 200, installed at a particular facility, installation site, and/or geographic location. In such an embodiment, the single edge agent 200 is configured to receive logging data from all specified industrial machines 10 installed at the facility and/or sensor information from sensors 200 that are associated with one or more of industrial machines 10 installed at the facility, which can be the same as, greater than, or less than the quantity of the specified industrial machines 10. In some embodiments, the industrial machines 10 on which the sensors 200 are installed, or with which the sensors 200 are associated (e.g., sufficiently proximate to, allowing for detection of one or more operational parameters thereof), are entirely different from the specified industrial machines 10 from which the edge agent 10 is configured to receive logging data, meaning that none of such specified industrial machines 10 have any sensors 200 (e.g., no additional sensors, beyond those sensors that are provided by a manufacturer of such specified industrial machines 10) associated therewith.
In some embodiments, there are a plurality of edge agents 100, with or without any sensors 200, installed at a particular facility, installation site, and/or geographic location. In some such embodiments, each edge agent 100 is configured to receive logging data from a subset of (e.g., less than all of) the industrial machines 10 and/or from a subset of (e.g., less than all of) the sensors 200 located at the facility, installation site, and/or geographic location. In some other such embodiments, all of the edge agents 100 are connected to, and in communication with, all of the industrial machines 10 and/or all of the sensors 200 located at the facility, installation site, and/or geographic location.
In any of such embodiments, the edge agents 100 may be provided in a redundant manner, so that multiple edge agents 100 are in communication with each industrial machine 10 and/or sensor 200 and may be configured such that the redundant edge agents 100 operate concurrently with (e.g., simultaneously with) the primary redundant edge agents 100, the redundant edge agents 100 only transmitting logging data and/or sensor information to the one or more central controllers associated therewith upon a failure, fault condition, malfunction, etc. being detected in a corresponding one of the primary edge agents 100. In other redundant operating modes, the redundant edge agents 100 may be kept in a sleep, hibernate, low power, or off state until a failure, fault condition, malfunction, etc. is detected in a corresponding one of the primary edge agents 100. In some such embodiments, the primary and redundant edge agents 100 are connected to the one or more central controllers 300 by different communication networks. Examples of such different communication networks can include different connection types to a same communication network (e.g., wireless and wired connections to the Internet, in which the wireless connection is used as a redundant communication connection for transmitting logging data to the one or more central controllers 300 upon failure of the wired connection) or an entirely different communication network (e.g., the Internet as the communication network for the primary edge agents 100 and a satellite-based data transmission network for the redundant edge agents 100). In some embodiments, the primary edge agents 100 are connected to only the primary communication network 50 and the redundant edge agents 100 are connected to both the primary and secondary communication networks 50.
In some embodiments, there is only a single edge agent 100 for each industrial machine 100 installed at a particular facility, installation site, and/or geographic location. In such embodiments having one or more edge agents 100 dedicated to a single industrial machine 10, each edge agent 100 is configured to receive logging data from a different one of a plurality of industrial machines 10 (e.g., every edge agent 100 is attached to and/or is in communication with and configured to receive logging data from only one industrial machine 10, which does not send any logging data to any other edge agent 100). In such embodiments, a single edge agent 100 can be associated with a single sensor 200 or one or more sensors 200. In some embodiments, the sensors 200 may be in the form of an SoC with a processor, memory, a transceiver, and the like and configured to process the sensor information and act as a de facto edge agent, communicating directly with the one or more central controllers 300 (e.g., via the communication network 50).
In some embodiments, the system 1 has a plurality of central controllers 300, which are configured to work separately from each other or together (e.g., as a redundant network of central controllers 300). In an example embodiment having redundant operation, one of (or a subset of) a plurality of central controllers 300 is designated as a primary central controller 300 and another of (or a subset of) the plurality of central controllers 300 is designated as a redundant central controller 300. The primary and redundant central controllers 300 are configured to not both operate at a same time (e.g., the primary and redundant central controllers 300 do not operate concurrently or simultaneously) and, upon failure of any of the primary central controllers 300, one of the redundant central controllers 300 is activated to assume the functionality previously performed by the failed primary central controller 300. Such an arrangement is advantageous in providing redundancy when a failure occurs. In some embodiments, the system 1 has a plurality of central controllers 300, each of which is simultaneously operable (e.g., active, turned on, initialized, etc.) to load balance the quantity of edge agents 100 and/or sensors 200 from which the central controller 300 is currently receiving logging data and/or sensor information. Thus, the plurality of central controllers 300 are configured to dynamically reassign edge agents 100 and/or sensors 200 to another of the plurality of central controllers 300 based on the quantity of edge agents 100 and/or sensors 200 with which each central controller 300 is in communication, so that each central controller 300 has substantially the same quantity (e.g., a same quantity per processor, allowing for variations of ±1) of edge agents 100 and/or sensors 200 associated therewith.
In
As shown in
In an advantageous example embodiment, the system 1 is configured such that the central controllers 300 are configured to transmit one or more commands, such as, for example and without limitation, command(s) to power off, power on, power cycle, and/or control operation of (e.g., start and/or stop) a part or component associated with any of the plurality of industrial machines 10 that receives the one or more commands and with which the central controller 300 is in communication via one or more edge agents 100. For example, if one of the central controllers 300 receives logging data indicating that one of the industrial machines 10 is in an error condition and then determines that a possible solution to resolve the error condition is to initiate a power cycle for the affected industrial machine 10, the central controller 300 is configured to transmit a power cycle command to the affected industrial machine 10, via the communication network 50 and one or more of the edge agents 100, in an attempt to resolve the error condition. As such, the power cycle command is transmitted through the communications network 50 to one of the edge agents 100 that is in bi-directional communication with the affected industrial equipment 10 and the edge agent 100 is configured to transmit the power cycle command to the affected industrial machine 10.
In some embodiments, the edge agents 100 are configured to transmit and receive communications, including logging data, instructions, and other network communications between the industrial machines 10 and the central controllers 300. In some other embodiments, the edge agents 100 are configured to control some of the processes running on the industrial machines 10. In such an embodiment, the edge agents 100 are configured to be able to initiate, for any of the industrial machines 10, a command to power off, power on, power cycle, switch networks, run repair subroutines, etc. based on the command(s) received from the central controllers 300 and the control capabilities of the edge agent 100. For example, some edge agents 100 may have more or different control capabilities than other edge agents 100 depending on the type and design of each edge agent 100.
The central controllers 300, which can be so-called “cloud” devices, can be configured to control the edge agents 100 and the edge agents 100 can be configured to control the industrial machines 10. For example and without limitation, the central controllers 300 can be configured to restart, reinitialize, and/or reconfigured the edge agents 100 remotely (e.g., from or via the cloud). The edge agents 100, based on algorithms, are able to send commands to execute functions on the industrial equipment 10 via the edge agents 100, such as, for example, power cycle an industrial machine 10 or move a feeding and/or cutting mechanism to a certain position/status.
In some embodiments, the edge agents 100 are configured to collect logging data from one or more pieces of the industrial equipment 10 and/or sensor information from one or more sensors 200. For example, the edge agents 100 are configured to proactively monitor (e.g., search for) configured files where the industrial equipment 10 is configured to write logging data (e.g., error logs, status, and/or error messages) during operation of the industrial equipment 10. The edge agents may, in some embodiments, be configured to receive sensor information from the sensors 200. The logging data and/or the sensor information are monitored continuously by an associated one of the edge agents 100 of the system 1 and is transmitted (e.g., streamed in real-time) to a central controller 300, where further filtering and transformation of the logging data and/or sensor information occurs in real-time. The edge agents 100 and the central controllers 300 are configured to monitor logging data and/or sensor information and to issue commands on the basis of the same, based on the types of industrial machines for which such logging data and/or sensor information is being generated.
In some embodiments, the contents of the logging data are heterogeneous in nature, meaning each industrial machine 10 is generating logging data (e.g., errors, or error messages), in a proprietary format that is different from other industrial machines 10, even other industrial machines 10 of a same type. The proprietary format depends largely on how the manufacturer elected to implement data logging functionality. There is currently no standard method of writing such logging data, even between different manufacturers of the same type of industrial machine. These logs were typically intended for use in a so-called “debug” process and were often never intended for real-time data analytics usage.
In some such embodiments, the logging data must be decoded and then re-encoded to a standardized messaging format. This requires initial data modeling during design and implementation of such systems and methods, then automation to perform the functionality disclosed herein, which will be scripted in the system process. In addition, data modelling requires knowledge of the each particular type of industrial machine, error conditions, and possible corrective actions associated therewith.
Using the transceiver 320, the central controller 300 is configured to receive logging data and/or sensor information from the edge agents 100 with which the central controller 300 is in communication and to process the logging data and/or sensor information as described herein. In some embodiments, the central controller 300 is configured to process logging data and/or sensor information received from the edge agents 100 as described herein and perform predictive failure analysis to calculate a remaining useful life of a part or component of the industrial machine 10 based on the logging data and/or sensor information received and processed by the central controller 300. The central controller 300 is configured to transform the received logging data and/or sensor information into standardized logging messages with a uniform, or standardized, format for each of the standardized logging messages. Once the predictive failure analysis is complete and the logging data and/or sensor information are processed (e.g., fully processed), the central controller 300 is configured to transmit any necessary commands to any edge agents 100 that are associated with (e.g., in communication with and/or controlled by) the central controller 300 to perform necessary tasks to correct or prevent any current or anticipated error conditions in the industrial machines 10.
In some embodiments, the tasks necessary to be performed to correct or prevent the occurrence of a current or anticipated error condition requires coordination with other industrial machines 10, such as, for example, stopping operation of industrial machines 10 that are part of an assembly line with the affected industrial machine and whose continued operation while the necessary tasks are performed on the affected industrial machine 10 would be undesirable. In some embodiments, a current or anticipated error condition for one or more industrial machines 10 requires the performance of more complicated tasks, such that the central controller 300 is configured to transmit an alarm, warning, notification, message, etc. to a user (i.e., a technician, engineer, maintenance crew member, etc.) of the system 1, which instructs the user to perform a particular task, or sequence of tasks, on one or more of the industrial machines 10 to correct or prevent the occurrence of any current or anticipated error conditions. In some embodiments, the central controller 300 is configured to automatically generate work orders for the user, which include specific instructions to perform one or more tasks, or sequence of tasks, on the affected industrial equipment 10, as determined by the processing of the logging data and/or sensor information by the central controller 300.
In the example embodiment shown in
The remainder of the description of
A sixth step 812 of the method 800 comprises receiving, via one or more transceivers of each edge agent, sensor information from the one or more sensors and/or logging messages from one or more of the plurality of industrial machines, wherein the sensor information and the logging messages contain information regarding one or more of the plurality of industrial machines. A seventh step 814 of the method 800 comprises connecting one or more central controllers in communication with the one or more edge agents. An eighth step 816 of the method 800 comprises transmitting, between the one or more transceivers of each edge agent and one or more transceivers of the one or more central controllers, the logging messages and the sensor information. A ninth step 818 of the method 800 comprises transforming, using the one or more central controllers, the logging messages and the sensor information into standardized logging messages, each of which has a same formatting.
A tenth step 820 of the method 800 comprises analyzing, using the one or more central controllers, the standardized logging messages to determine a current or anticipated error condition associated with one or more of the plurality of industrial machines. An eleventh step 822 of the method 800 comprises transmitting, automatically and via the one or more transceivers of the one or more central controllers, an alert or a notification regarding the current or anticipated error condition to one or more displays. A twelfth step 824 of the method 800 comprises displaying, on the one or more displays, the alert or the notification to one or more users.
The central controller transforms the logs into standardized logging messages, each of which has a standardized format. The standardized format is based on the data model created for the industrial machine. A custom code (e.g., a set or sets of executable instructions) can run on the central controller and search for commonality among various entries (e.g., messages) in the logging data and then convert these common entries into a standardized format. For example, since each industrial machine of a different type and/or manufacturer is unique in the way that logging data is generated, the logging data is usable with and through a data engineering process to identify the logging data of interest, based on predetermined use cases for remote monitoring and analytics. When the logging data of interest is identified in various parts of a log file (e.g., an unstructured log file), the logging data of interest is extracted using scripts (e.g., a set or sets of executable instructions) and data transformation methods in real-time. These extracted data elements are then stored in a structured database, which is accessible to the central controllers for executing algorithms to perform the necessary computations in determining the presence of a current or anticipated error condition.
Thus, a thirteenth step 826 of the method 800 comprises providing, in communication with the one or more central controllers, a database that includes entries of historical error conditions, as well as historical logging messages that were generated before, during, and/or after each instance of the historical error conditions, for any of the plurality of industrial machines. A fourteenth step 828 of the method 800 comprises determining, using the one or more central controllers, the current or anticipated error condition by comparing the standardized logging messages to the logging messages associated with the historical error conditions in the database. A fifteenth step 830 of the method 800 comprises comparing, using the one or more central controllers, the standardized logging messages to the historical logging messages associated with the historical error conditions in the database to identify strings of logging messages in the standardized logging messages that are substantially identical to the logging messages associated with the historical error conditions in the database.
A sixteenth step 832 of the method 800 comprises comparing, using the one or more central controllers, the standardized logging messages to the logging messages associated with the historical error conditions in the database to identify strings of logging messages in the standardized logging messages that are identical to the logging messages associated with the historical error conditions in the database. A seventeenth step 834 of the method 800 comprises transmitting, using the one or more central controllers, one or more commands to any of the plurality of industrial machines for which the current or anticipated error condition is generated. An eighteenth step 836 of the method 800 comprises automatically performing, for any of the plurality of industrial machines that receives the one or more commands, one or more actions to correct, or prevent an occurrence of, the current or anticipated error condition. A nineteenth step 838 of the method 800 comprises generating, using the one or more central controllers, a work order for any of the plurality of industrial machines with which a current or anticipated error condition is associated, wherein the work order comprises instructions for a service technician to perform to correct, or prevent an occurrence of, the current or anticipated error condition. A twentieth step 840 of the method 800 comprises transmitting the work order to the service technician. A twenty-first step 842 of the method 800 comprises receiving, at the one or more displays, information regarding a performance of one or more of the plurality of industrial machines. A twenty-second step 844 of the method 800 comprises displaying, on the one or more displays, the information regarding the performance of the one or more of the plurality of industrial machines.
In some embodiments, a composite logging message (e.g., a composite standardized logging message) can be generated based on analyzing one or more entries of logging data and/or sensor information received from any of the edge agents 100. Thus, instead of the one-to-one ratio of standardized logging messages to un-processed entries of logging data and/or sensor information, the ratio is less than a one-to-one ratio, meaning that fewer standardized logging messages are generated than there are entries of logging data and/or sensor information received. In some embodiments, after the key insights from the un-processed logging data and/or sensor information are extracted and transformed into standardized logging messages, the central controller 300 is configured to analyze the standardized logging messages using various algorithms (e.g., which can be stored in a memory thereof) to determine whether the standardized logging messages indicate the a current or anticipated error condition is occurring or is likely to occur within a prescribed or specified period of time at the industrial machine 10 associated with the logging data and/or sensor information.
In order to determine whether the standardized logging messages indicate the occurrence of a current or future error condition on the industrial machine 10, the central controller 300 is configured to communicate with a database containing entries of historical error conditions associated with industrial machines 10 of a particular type and/or manufacturer and also the standardized logging messages, logging data, and/or sensor information associated with (e.g., generated before, during, and/or after the occurrence of) the historical error conditions from which the logging data and/or sensor information was received. The central controller 300 is configured to query search, or cross-reference) the entries contained within this database and to compare currently received standardized logging messages, logging data, and/or sensor information to the entries of the same, or substantially similar, instances or strings of standardized logging messages, logging data, and/or sensor information that were generated during a known historical error condition to analyze patterns of matching sequences of standardized logging messages, logging data, and/or sensor information associated with particular instances of historical error conditions. In some embodiments, the central controller 300 utilizes machine learning and other analytical techniques to better understand the entries, or sequences thereof, of sequences of standardized logging messages, logging data, and/or sensor information being received and how such entries or sequences of entries compare to the standardized logging messages, logging data, and/or sensor information associated with the historical error conditions stored in the database. Thus, the central controller 300 is configured to learn from and adapt to the patterns of standardized logging messages, logging data, and/or sensor information stored in the database associated with historical error conditions to be able to detect the occurrence of current or anticipated error conditions in the currently received standardized logging messages, logging data, and/or sensor information based on the ongoing analysis of the data stored in the database.
The central controller 300 is configured to process the standardized logging messages, the logging data, and/or the sensor information to determine the occurrence of a current or anticipated error condition in any industrial machine 10 from which the central controller 300 is receiving such logging data and/or sensor information. When the central controller 300 receives logging data and/or sensor information from an edge agent 100, the central controller 300 is configured to determine that such logging data and/or sensor information is a part of a sequence that corresponds to (e.g., is transmitted before, during, and/or after) the standardized logging messages, logging data, and/or sensor information contained within the database and associated with an error condition for an industrial machine 10 of a same type and/or manufacturer.
The raw, or unprocessed, logging data and/or sensor information is received and transformed into one or more (e.g., a plurality of) standardized logging messages that are in a standard format. These standardized logging messages are then analyzed by the central controller 300, which executes one or more algorithms based on use case (e.g., the type, manufacturer, and/or task being performed by an industrial machine 10). For example,
However, in some instances, such current or anticipated error conditions require physical intervention by a user (e.g., service personnel or end-user) at the physical location of the affected industrial equipment 10, in which case the central controller 300 is configured to transmit commands (e.g., messages and/or instructions) to a user of the system 1 or the affected industrial equipment 10. In some embodiments, the commands sent to the user comprise instructions to power off, power on, power cycle, start or stop instructions, or instructions to alter operation of one or more components of the affected industrial machine 10. In some instances, the commands transmitted to the user comprise instructions regarding how to fix or replace one or more components of the affected industrial machine 10, how to address (e.g., remove) a material jam (e.g., a paper jam or other material jam), how to reconfigure the affected industrial machine 10, and/or how to otherwise alter the affected industrial machine 10, or the operation of the affected industrial machine 10, to resolve or prevent the occurrence of any such current or anticipated error condition.
In some embodiments, the commands sent to the user by the central controller 300 comprise an alert, notification, warning, alarm, and/or error message regarding the present or imminent occurrence of the current or anticipated error condition. The alert, notification, warning, alarm, and/or error message can be transmitted in any form and via any suitable communication medium, including, for example and without limitation, by email, automated phone call, text message (i.e., SMS), a pop-up on a terminal or screen, such as the display, a push notification on a mobile device, a warning or alarm sound on the affected industrial machine 10, edge agent 100, or other location, or any other suitable warning, alarm, or error message. In some embodiments, the central controller 300 is configured to transmit any of the messages, instructions, or warnings to the user's personal electronic device(s) (e.g., mobile phone, smart phone, tablet, PC, server, personal digital assistant, an FPGA, a monitor, or any other suitable device to which the user has access and is in a location where the user may see and/or interact with the warning, message, or notification).
In some embodiments, the central controller 300 is configured to automatically generate and transmit one or more work orders to fix or prevent an occurrence of a current or anticipated error condition for an affected industrial machine 10. In some such embodiments, the central controller 300 is configured to generate and transmit such work orders to users, engineers, service technicians, and the like to fix the current or anticipated error condition identified by the central controller 300 on the industrial equipment and/or, in some instances, perform maintenance to prevent the occurrence of an anticipated error condition.
In some embodiments, the central controller 300 is configured to transmit performance data regarding any industrial machine 10 with which the central controller 300 is in communication to a display 500, or other suitable user terminal, for viewing and monitoring (e.g., by service personnel).
The present subject matter can be embodied in other forms without departure from the spirit and essential characteristics thereof. The embodiments described therefore are to be considered in all respects as illustrative and not restrictive. Although the present subject matter has been described in terms of certain specific embodiments, other embodiments that are apparent to those of ordinary skill in the art are also within the scope of the present subject matter.
This patent application claims priority to U.S. Provisional Patent Application Ser. No. 63/187,640, filed on May 12, 2021, the entire content of which is incorporated by reference herein.
| Number | Date | Country | |
|---|---|---|---|
| 63187640 | May 2021 | US |
